Is Qwen3.5-9B-heretic-v2 or Qwen3-30B-A3B-Thinking-2507 smaller?

Qwen3.5-9B-heretic-v2 is smaller at Q4_K_M: 5.24 GiB against 17.28 GiB.

Which uses less memory at long context?

Qwen3.5-9B-heretic-v2 — its KV cache at 32K context is 3.0x smaller, because of how its attention layers cache.

Model comparison

Qwen3.5-9B-heretic-v2 vs Qwen3-30B-A3B-Thinking-2507

At Q4_K_M, Qwen3.5-9B-heretic-v2 is the smaller download — 5,627,044,352 bytes against 18,556,685,824. At long context the gap widens: Qwen3.5-9B-heretic-v2's KV cache at 32K is 3.0× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Qwen3.5-9B-heretic-v2	Qwen3-30B-A3B-Thinking-2507
Parameters	9.4B	30.5B
Architecture	qwen35	qwen3moe
Layers	32	48
Native context	262,144	262,144
Mixture of experts	no	yes, 128 experts
Quantizations published	9	51
Smallest quantization	5.24 GiB	7.05 GiB
Q4_K_M	5.24 GiB	17.28 GiB
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Qwen3.5-9B-heretic-v2	Qwen3-30B-A3B-Thinking-2507	Ratio
4,096	0.13 GiB	0.38 GiB	3.00×
8,192	0.25 GiB	0.75 GiB	3.00×
16,384	0.50 GiB	1.50 GiB	3.00×
32,768	1.00 GiB	3.00 GiB	3.00×
65,536	2.00 GiB	6.00 GiB	3.00×
131,072	4.00 GiB	12.00 GiB	3.00×